The current success of machine learning on image-based combustion monitoring is based on massive data, which is costly even impossible for industrial applications. To address this conflict, we introduce few-shot learning in order to achieve combustion monitoring and classification for the first time. Two algorithms, Siamese Network coupled with k Nearest Neighbors (SN-kNN) and Prototypical Network (PN), were tested. Rather than utilizing solely visible images as discussed in previous studies, we also used Infrared (IR) images. We analyzed the training process, test performance and inference speed of two algorithms on both image formats, and also used t-SNE to visualize learned features. The results demonstrated that both SN-kNN and PN were capable to distinguish flame states from learning with merely 20 images per flame state. The worst performance, which was realized by PN on IR images, still possessed precision, accuracy, recall, and F1-score above 0.95. We showed that visible images demonstrated more substantial differences between classes and presented more consistent patterns inside the class, which made the training speed and model performance better compared to IR images. In contrast, the relatively low quality of IR images made it difficult for PN to extract distinguishable prototypes, which caused relatively weak performance. With the entrire training set supporting classification, SN-kNN performed well with IR images. On the other hand, benefitting from the architecture design, PN has a much faster speed in training and inference than SN-kNN. The presented work analyzed the characteristics of both algorithms and image formats for the first time, thus providing guidance for their future utilization in combustion monitoring tasks.
翻译:在基于图像的燃烧监测方面,机器学习目前的成功是基于大量数据,这种数据甚至对工业应用来说代价昂贵,甚至是不可能的。为了解决这一冲突,我们引入了几张短片学习,以便首次实现燃烧监测和分类。测试了两个算法,即Siamese 网络,加上K Nearest Gearbidbors (SN-kNNN)和Protodom Network(PN)。我们使用红外线图像,不是仅仅使用以往研究中所讨论的可见图像,而是使用红外线(IR)图像。我们分析了两个算法的培训过程、测试性能和推断速度,并且还使用T-SNE来将所学的特征进行视觉化。结果显示,SN-kNNNN和PNP能够区分火焰状态,而每个火焰状态只有20个图像的学习。PN的性能最差在于PN仍然具有精确性能、准确性能、回顾和F1-核心图像高于0.95。我们发现,可见的图像显示了班内班级之间差异更大,并且显示更加一致的模式,使得培训速度和模型的性能和模型的性能都比IR的性能要好地更精确地显示SNNNR图像的性,因此使得其设计质量比SNNR的图像在设计上较差。因此,因此较低的图像的性能对SL的性能进行了较低的性能进行了较差。